Nowcasting dan Forecasting Pertumbuhan Produk Domestik Bruto Indonesia Menggunakan MIDAS-ARIMA

Ulunalfat, Nashru (2025) Nowcasting dan Forecasting Pertumbuhan Produk Domestik Bruto Indonesia Menggunakan MIDAS-ARIMA. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5003211127-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (5MB) | Request a copy

Abstract

Produk Domestik Bruto (PDB) adalah indikator makroekonomi penting untuk menilai kinerja ekonomi suatu negara. Namun, keterlambatan dalam data PDB triwulanan sering kali menghambat pengambilan keputusan yang tepat waktu. Penelitian ini bertujuan untuk mengatasi masalah tersebut dengan menggunakan model nowcasting berbasis metode Mixed Data Sampling Autoregressive Integrated Moving Average (MIDAS-ARIMA), yang mengintegrasikan data frekuensi tinggi (indikator ekonomi bulanan) untuk memberikan estimasi pertumbuhan PDB sebelum data resmi dirilis. Penelitian ini menggunakan data bulanan dari Januari 2001 hingga Maret 2025 dan data triwulanan dari 2001 hingga 2024. Tujuan penelitian adalah untuk mengetahui hasil nowcasting dan forecasting pertumbuhan PDB bulanan serta mengevaluasi akurasi prediksi model. Hasil evaluasi menunjukkan bahwa model MIDAS dengan kombinasi δ1=-1 dan δ2=-1 sebagai fungsi pembobot Eksponential Almon Lag Polynomial memberikan performa terbaik dengan nilai AIC dan BIC terkecil dibandingkan model lainnya. Model ini secara efektif memperkirakan pertumbuhan PDB bulanan dengan nilai nowcasting untuk bulan Januari, Februari, dan Maret tahun 2025 secara berturut-turut adalah -0,6960470, -0,5414669, dan -0,5382004. Sementara itu, model ARIMA(0,1,[2,3])(0,1,1)12 terpilih untuk meramalkan pertumbuhan PDB bulanan dengan menghasilkan nilai forecasting pertumbuhan PDB bulanan untuk bulan April, Mei, dan Juni tahun 2025 berturut-turut adalah 2,2703076, 2,3474538, dan 2,3491110. Penelitian ini diharapkan memberikan kontribusi signifikan terhadap perencanaan kebijakan pemerintah dan memperkaya analisis data deret waktu.
==================================================================================================================================
Gross Domestic Product (GDP) is a crucial macroeconomic indicator that reflects the economic performance of a country. However, the delay in the release of quarterly GDP data often hampers timely decision-making. This study aims to address this issue by utilizing a nowcasting model based on the Mixed Data Sampling Autoregressive Integrated Moving Average (MIDAS-ARIMA) method, which integrates high-frequency data (monthly economic indicators) to provide real-time estimates of GDP growth before official data is released. The study uses monthly data from January 2001 to March 2025 and quarterly data from 2001 to 2024. The objectives of this study are to assess the nowcasting and forecasting results of quarterly GDP growth and to evaluate the prediction accuracy of the model. The evaluation results show that the MIDAS model with a combination of δ1=-1 and δ2=-1 as the Exponential Almon Lag Polynomial weighting function provides the best performance with the smallest AIC and BIC values compared to other models. This model effectively estimates monthly GDP growth with nowcasting values for January, February, and March 2025 of -0,6960470, -0,5414669, and -0,5382004, respectively. Meanwhile, the ARIMA(0,1,[2,3])(0,1,1)12 model was selected to estimate monthly GDP growth by producing monthly GDP growth forecast values for April, May, and June 2025 of 2,2703076, 2,3474538, and 2,3491110, respectively. This research is expected to provide significant contributions to planning, government policy, and the welfare of data analysis over time.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Nowcasting, Pertumbuhan PDB, Mixed Data Sampling (MIDAS), ARIMA, Peramalan Ekonomi, Deret Waktu, Nowcasting, GDP Growth, Mixed Data Sampling (MIDAS), ARIMA, Economic Forecasting, Time Series
Subjects:	Q Science > QA Mathematics > QA276 Mathematical statistics. Time-series analysis. Failure time data analysis. Survival analysis (Biometry)
Divisions:	Faculty of Mathematics and Science > Statistics > 49201-(S1) Undergraduate Thesis
Depositing User:	Nashru Ulunalfat
Date Deposited:	01 Aug 2025 05:52
Last Modified:	01 Aug 2025 05:52
URI:	http://repository.its.ac.id/id/eprint/125616

Actions (login required)

View Item